In this notebook, some template code has already been provided for you, and you will need to implement additional functionality to successfully complete this project. You will not need to modify the included code beyond what is requested. Sections that begin with '(IMPLEMENTATION)' in the header indicate that the following block of code will require additional functionality which you must provide. Instructions will be provided for each section, and the specifics of the implementation are marked in the code block with a 'TODO' statement. Please be sure to read the instructions carefully!
Note: Once you have completed all of the code implementations, you need to finalize your work by exporting the Jupyter Notebook as an HTML document. Before exporting the notebook to html, all of the code cells need to have been run so that reviewers can see the final implementation and output. You can then export the notebook by using the menu above and navigating to File -> Download as -> HTML (.html). Include the finished document along with this notebook as your submission.
In addition to implementing code, there will be questions that you must answer which relate to the project and your implementation. Each section where you will answer a question is preceded by a 'Question X' header. Carefully read each question and provide thorough answers in the following text boxes that begin with 'Answer:'. Your project submission will be evaluated based on your answers to each of the questions and the implementation you provide.
Note: Code and Markdown cells can be executed using the Shift + Enter keyboard shortcut. Markdown cells can be edited by double-clicking the cell to enter edit mode.
The rubric contains optional "Stand Out Suggestions" for enhancing the project beyond the minimum requirements. If you decide to pursue the "Stand Out Suggestions", you should include the code in this Jupyter notebook.
In this notebook, you will make the first steps towards developing an algorithm that could be used as part of a mobile or web app. At the end of this project, your code will accept any user-supplied image as input. If a dog is detected in the image, it will provide an estimate of the dog's breed. If a human is detected, it will provide an estimate of the dog breed that is most resembling. The image below displays potential sample output of your finished project (... but we expect that each student's algorithm will behave differently!).

In this real-world setting, you will need to piece together a series of models to perform different tasks; for instance, the algorithm that detects humans in an image will be different from the CNN that infers dog breed. There are many points of possible failure, and no perfect algorithm exists. Your imperfect solution will nonetheless create a fun user experience!
We break the notebook into separate steps. Feel free to use the links below to navigate the notebook.
Make sure that you've downloaded the required human and dog datasets:
Download the dog dataset. Unzip the folder and place it in this project's home directory, at the location /dogImages.
Download the human dataset. Unzip the folder and place it in the home directory, at location /lfw.
Note: If you are using a Windows machine, you are encouraged to use 7zip to extract the folder.
In the code cell below, we save the file paths for both the human (LFW) dataset and dog dataset in the numpy arrays human_files and dog_files.
import numpy as np
from glob import glob
# load filenames for human and dog images
human_files = np.array(glob("lfw/*/*"))
dog_files = np.array(glob("dogImages/*/*/*"))
# print number of images in each dataset
print('There are %d total human images.' % len(human_files))
print('There are %d total dog images.' % len(dog_files))
There are 13233 total human images. There are 8351 total dog images.
In this section, we use OpenCV's implementation of Haar feature-based cascade classifiers to detect human faces in images.
OpenCV provides many pre-trained face detectors, stored as XML files on github. We have downloaded one of these detectors and stored it in the haarcascades directory. In the next code cell, we demonstrate how to use this detector to find human faces in a sample image.
import cv2
import matplotlib.pyplot as plt
%matplotlib inline
# extract pre-trained face detector
face_cascade = cv2.CascadeClassifier('haarcascades/haarcascade_frontalface_alt.xml')
# load color (BGR) image
img = cv2.imread(human_files[0])
# convert BGR image to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# find faces in image
faces = face_cascade.detectMultiScale(gray)
# print number of faces detected in the image
print('Number of faces detected:', len(faces))
# get bounding box for each detected face
for (x,y,w,h) in faces:
# add bounding box to color image
cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
# convert BGR image to RGB for plotting
cv_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# display the image, along with bounding box
plt.imshow(cv_rgb)
plt.show()
Number of faces detected: 1
faces
array([[ 71, 68, 110, 110]], dtype=int32)
Before using any of the face detectors, it is standard procedure to convert the images to grayscale. The detectMultiScale function executes the classifier stored in face_cascade and takes the grayscale image as a parameter.
In the above code, faces is a numpy array of detected faces, where each row corresponds to a detected face. Each detected face is a 1D array with four entries that specifies the bounding box of the detected face. The first two entries in the array (extracted in the above code as x and y) specify the horizontal and vertical positions of the top left corner of the bounding box. The last two entries in the array (extracted here as w and h) specify the width and height of the box.
We can use this procedure to write a function that returns True if a human face is detected in an image and False otherwise. This function, aptly named face_detector, takes a string-valued file path to an image as input and appears in the code block below.
# returns "True" if face is detected in image stored at img_path
def face_detector(img_path):
img = cv2.imread(img_path)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray)
return len(faces) > 0
Question 1: Use the code cell below to test the performance of the face_detector function.
human_files have a detected human face? dog_files have a detected human face? Ideally, we would like 100% of human images with a detected face and 0% of dog images with a detected face. You will see that our algorithm falls short of this goal, but still gives acceptable performance. We extract the file paths for the first 100 images from each of the datasets and store them in the numpy arrays human_files_short and dog_files_short.
Answer:
Total of 96 out of 100 human images was detected correctly
Total of 18 out of 100 dog images was detected incorrect
from tqdm import tqdm
human_files_short = human_files[:100]
dog_files_short = dog_files[:100]
#-#-# Do NOT modify the code above this line. #-#-#
## TODO: Test the performance of the face_detector algorithm
human_result = []
for img in human_files_short:
human_result.append(face_detector(img))
print(f'Total of {sum(human_result)} out of {len(human_result)} human images was detected correctly')
dog_result = []
for img in dog_files_short:
dog_result.append(face_detector(img))
print(f'Total of {sum(dog_result)} out of {len(dog_result)} dog images was detected incorrect')
## on the images in human_files_short and dog_files_short.
Total of 96 out of 100 human images was detected correctly Total of 18 out of 100 dog images was detected incorrect
We suggest the face detector from OpenCV as a potential way to detect human images in your algorithm, but you are free to explore other approaches, especially approaches that make use of deep learning :). Please use the code cell below to design and test your own face detection algorithm. If you decide to pursue this optional task, report performance on human_files_short and dog_files_short.
### (Optional)
### TODO: Test performance of another face detection algorithm.
### Feel free to use as many code cells as needed.
In this section, we use a pre-trained model to detect dogs in images.
The code cell below downloads the VGG-16 model, along with weights that have been trained on ImageNet, a very large, very popular dataset used for image classification and other vision tasks. ImageNet contains over 10 million URLs, each linking to an image containing an object from one of 1000 categories.
import torch
import torchvision.models as models
# define VGG16 model
VGG16 = models.vgg16(pretrained=True)
# check if CUDA is available
use_cuda = torch.cuda.is_available()
# move model to GPU if CUDA is available
if use_cuda:
VGG16 = VGG16.cuda()
print('GPU is availble')
GPU is availble
VGG16
VGG(
(features): Sequential(
(0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU(inplace=True)
(4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(6): ReLU(inplace=True)
(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(8): ReLU(inplace=True)
(9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU(inplace=True)
(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(13): ReLU(inplace=True)
(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(15): ReLU(inplace=True)
(16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(18): ReLU(inplace=True)
(19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(20): ReLU(inplace=True)
(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(22): ReLU(inplace=True)
(23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(25): ReLU(inplace=True)
(26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(27): ReLU(inplace=True)
(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(29): ReLU(inplace=True)
(30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
(avgpool): AdaptiveAvgPool2d(output_size=(7, 7))
(classifier): Sequential(
(0): Linear(in_features=25088, out_features=4096, bias=True)
(1): ReLU(inplace=True)
(2): Dropout(p=0.5, inplace=False)
(3): Linear(in_features=4096, out_features=4096, bias=True)
(4): ReLU(inplace=True)
(5): Dropout(p=0.5, inplace=False)
(6): Linear(in_features=4096, out_features=1000, bias=True)
)
)
Given an image, this pre-trained VGG-16 model returns a prediction (derived from the 1000 possible categories in ImageNet) for the object that is contained in the image.
In the next code cell, you will write a function that accepts a path to an image (such as 'dogImages/train/001.Affenpinscher/Affenpinscher_00001.jpg') as input and returns the index corresponding to the ImageNet class that is predicted by the pre-trained VGG-16 model. The output should always be an integer between 0 and 999, inclusive.
Before writing the function, make sure that you take the time to learn how to appropriately pre-process tensors for pre-trained models in the PyTorch documentation.
from PIL import Image
import torchvision.transforms as transforms
# Set PIL to be tolerant of image files that are truncated.
from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True
def VGG16_predict(img_path):
'''
Use pre-trained VGG-16 model to obtain index corresponding to
predicted ImageNet class for image at specified path
Args:
img_path: path to an image
Returns:
Index corresponding to VGG-16 model's prediction
'''
# Load the image
img = Image.open(img_path)
# preprocessing steps
# 1- Initialize normalizer object
normalizer = transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
# 2- Set the tranformer object
transform = transforms.Compose(
[transforms.Resize(224),
transforms.ToTensor(),
normalizer]
)
## TODO: Complete the function.
## Load and pre-process an image from the given img_path
image = transform(img)[:3,:,:].unsqueeze(0)
## Return the *index* of the predicted class for that image
use_cuda = torch.cuda.is_available()
if use_cuda:
image = image.cuda()
pred = VGG16(image)
pred = pred.cpu().data.numpy().argmax()
return pred # predicted class index
While looking at the dictionary, you will notice that the categories corresponding to dogs appear in an uninterrupted sequence and correspond to dictionary keys 151-268, inclusive, to include all categories from 'Chihuahua' to 'Mexican hairless'. Thus, in order to check to see if an image is predicted to contain a dog by the pre-trained VGG-16 model, we need only check if the pre-trained model predicts an index between 151 and 268 (inclusive).
Use these ideas to complete the dog_detector function below, which returns True if a dog is detected in an image (and False if not).
### returns "True" if a dog is detected in the image stored at img_path
def dog_detector(img_path):
## TODO: Complete the function.
pred = VGG16_predict(img_path)
return pred >= 151 and pred <= 268 # true/false
Question 2: Use the code cell below to test the performance of your dog_detector function.
human_files_short have a detected dog? dog_files_short have a detected dog?Answer:
dog percent is 95.0% ,and Human Percent is 0.0%
### TODO: Test the performance of the dog_detector function
### on the images in human_files_short and dog_files_short.
dog_pred = []
for img in dog_files_short:
dog_pred.append(dog_detector(img))
human_pred = []
for img in human_files_short:
human_pred.append(dog_detector(img))
print(f'dog percent is {(sum(dog_pred)/len(dog_pred))*100}% ,and Human Percent is { (sum(human_pred)/len(human_pred))*100}%')
dog percent is 95.0% ,and Human Percent is 0.0%
We suggest VGG-16 as a potential network to detect dog images in your algorithm, but you are free to explore other pre-trained networks (such as Inception-v3, ResNet-50, etc). Please use the code cell below to test other pre-trained PyTorch models. If you decide to pursue this optional task, report performance on human_files_short and dog_files_short.
### (Optional)
### TODO: Report the performance of another pre-trained network.
### Feel free to use as many code cells as needed.
Now that we have functions for detecting humans and dogs in images, we need a way to predict breed from images. In this step, you will create a CNN that classifies dog breeds. You must create your CNN from scratch (so, you can't use transfer learning yet!), and you must attain a test accuracy of at least 10%. In Step 4 of this notebook, you will have the opportunity to use transfer learning to create a CNN that attains greatly improved accuracy.
We mention that the task of assigning breed to dogs from images is considered exceptionally challenging. To see why, consider that even a human would have trouble distinguishing between a Brittany and a Welsh Springer Spaniel.
| Brittany | Welsh Springer Spaniel |
|---|---|
![]() |
![]() |
It is not difficult to find other dog breed pairs with minimal inter-class variation (for instance, Curly-Coated Retrievers and American Water Spaniels).
| Curly-Coated Retriever | American Water Spaniel |
|---|---|
![]() |
![]() |
Likewise, recall that labradors come in yellow, chocolate, and black. Your vision-based algorithm will have to conquer this high intra-class variation to determine how to classify all of these different shades as the same breed.
| Yellow Labrador | Chocolate Labrador | Black Labrador |
|---|---|---|
![]() |
![]() |
![]() |
We also mention that random chance presents an exceptionally low bar: setting aside the fact that the classes are slightly imabalanced, a random guess will provide a correct answer roughly 1 in 133 times, which corresponds to an accuracy of less than 1%.
Remember that the practice is far ahead of the theory in deep learning. Experiment with many different architectures, and trust your intuition. And, of course, have fun!
Use the code cell below to write three separate data loaders for the training, validation, and test datasets of dog images (located at dogImages/train, dogImages/valid, and dogImages/test, respectively). You may find this documentation on custom datasets to be a useful resource. If you are interested in augmenting your training and/or validation data, check out the wide variety of transforms!
import os
from torchvision import datasets
### TODO: Write data loaders for training, validation, and test sets
## Specify appropriate transforms, and batch_sizes
batch_size=20
data_dir= './dogImages'
normalizer = transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
# 2- Set the tranformer object
# Augmentation used for training only
train_transform = transforms.Compose([transforms.Resize((224,224)),
transforms.RandomRotation(25),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
normalizer])
# transfor for validation and test images without augmentation
transform = transforms.Compose([transforms.Resize((224,224)),
transforms.ToTensor(),
normalizer])
train_dataset = datasets.ImageFolder(os.path.join(data_dir, 'train/'), transform=train_transform)
valid_dataset = datasets.ImageFolder(os.path.join(data_dir, 'valid/'), transform=transform)
test_dataset = datasets.ImageFolder(os.path.join(data_dir, 'test/'), transform=transform)
train_loader=torch.utils.data.DataLoader(train_dataset,batch_size=batch_size,shuffle=True)
valid_loader=torch.utils.data.DataLoader(valid_dataset,batch_size=batch_size)
test_loader=torch.utils.data.DataLoader(test_dataset,batch_size=batch_size)
loaders_scratch={'train':train_loader,
'valid':valid_loader,
'test':test_loader}
Question 3: Describe your chosen procedure for preprocessing the data.
Answer:
I used for image resizeing transforms.Resize((224,224) to assure not it fits in the model then,
i decided to make Random Rotation and Random Flip as augmantation to prevent model over fitting.
Create a CNN to classify dog breed. Use the template in the code cell below.
import torch.nn as nn
import torch.nn.functional as F
# define the CNN architecture
class Net(nn.Module):
### TODO: choose an architecture, and complete the class
def __init__(self):
super(Net, self).__init__()
## Define layers of a CNN
self.conv1=nn.Conv2d(3,32,3,padding=1)
self.conv2=nn.Conv2d(32,32,3,padding=1)
self.conv3=nn.Conv2d(32,64,3,padding=1)
self.conv4=nn.Conv2d(64,64,3,padding=1)
self.conv5=nn.Conv2d(64,128,3,padding=1)
self.conv6=nn.Conv2d(128,128,3,padding=1)
self.conv7=nn.Conv2d(128,256,3,padding=1)
self.pool=nn.MaxPool2d(2,2)
self.fc1=nn.Linear(7*7*256,500)
self.fc2=nn.Linear(500,133)
self.dp=nn.Dropout(0.4)
def forward(self, x):
## Define forward behavior
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = self.dp(x)
x = self.pool(F.relu(self.conv3(x)))
x = self.pool(F.relu(self.conv4(x)))
x = self.dp(x)
x = self.pool(F.relu(self.conv5(x)))
x = F.relu(self.conv6(x))
x = self.dp(x)
x = F.relu(self.conv7(x))
x = x.view(x.size(0), -1)
x = F.relu(self.fc1(x))
x = self.dp(x)
x = self.fc2(x)
return x
#-#-# You do NOT have to modify the code below this line. #-#-#
# instantiate the CNN
model_scratch = Net()
# move tensors to GPU if CUDA is available
if use_cuda:
model_scratch.cuda()
Question 4: Outline the steps you took to get to your final CNN architecture and your reasoning at each step.
Answer:
I decided to make 7 layers of cnn since this what i saw best for execution time and best results for this project, since vgg16 having 16 layers i tried to be close to its architech in this scratch model.
Started with 3 as the image layers then designed layer in exponentiol of 2.
I decided to make dropout of 40% ,and applied it after 1,2 and 3,4 layers
We implemented two fully connected layers.
Used the Relu Activation function and applied the Maxpooling(2,2)
Use the next code cell to specify a loss function and optimizer. Save the chosen loss function as criterion_scratch, and the optimizer as optimizer_scratch below.
import torch.optim as optim
### TODO: select loss function
criterion_scratch = nn.CrossEntropyLoss()
### TODO: select optimizer
optimizer_scratch = optim.SGD(model_scratch.parameters(),lr=0.01)
Train and validate your model in the code cell below. Save the final model parameters at filepath 'model_scratch.pt'.
model_scratch.load_state_dict(torch.load('model_scratch.pt'))
<All keys matched successfully>
# the following import is required for training to be robust to truncated images
from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True
def train(n_epochs, loaders, model, optimizer, criterion, use_cuda, save_path):
"""returns trained model"""
# initialize tracker for minimum validation loss
valid_loss_min = np.Inf
for epoch in range(1, n_epochs+1):
# initialize variables to monitor training and validation loss
train_loss = 0.0
valid_loss = 0.0
###################
# train the model #
###################
model.train()
for batch_idx, (data, target) in enumerate(loaders['train']):
# move to GPU
if use_cuda:
data, target = data.cuda(), target.cuda()
## find the loss and update the model parameters accordingly
optimizer.zero_grad()
output=model(data)
loss=criterion(output, target)
loss.backward()
optimizer.step()
## record the average training loss, using something like
train_loss = train_loss + ((1 / (batch_idx + 1)) * (loss.data - train_loss))
######################
# validate the model #
######################
model.eval()
for batch_idx, (data, target) in enumerate(loaders['valid']):
# move to GPU
if use_cuda:
data, target = data.cuda(), target.cuda()
## update the average validation loss
output=model(data)
loss=criterion(output, target)
valid_loss = valid_loss + ((1 / (batch_idx + 1)) * (loss.data - valid_loss))
# print training/validation statistics
print('Epoch: {} \tTraining Loss: {:.6f} \tValidation Loss: {:.6f}'.format(
epoch,
train_loss,
valid_loss
))
## TODO: save the model if validation loss has decreased
if valid_loss <= valid_loss_min:
print(f'validation loss decreased from {valid_loss_min:.5f} to {valid_loss:.5f}')
torch.save(model.state_dict(), save_path)
valid_loss_min = valid_loss
# return trained model
return model
# train the model
model_scratch = train(15, loaders_scratch, model_scratch, optimizer_scratch,
criterion_scratch, use_cuda, 'model_scratch.pt')
# load the model that got the best validation accuracy
model_scratch.load_state_dict(torch.load('model_scratch.pt'))
Epoch: 1 Training Loss: 2.481721 Validation Loss: 4.231058 validation loss decreased from inf to 4.23106 Epoch: 2 Training Loss: 2.430090 Validation Loss: 4.180182 validation loss decreased from 4.23106 to 4.18018 Epoch: 3 Training Loss: 2.349206 Validation Loss: 4.220695 Epoch: 4 Training Loss: 2.301554 Validation Loss: 4.240373 Epoch: 5 Training Loss: 2.210253 Validation Loss: 4.202801 Epoch: 6 Training Loss: 2.196676 Validation Loss: 4.200104 Epoch: 7 Training Loss: 2.138934 Validation Loss: 4.188211 Epoch: 8 Training Loss: 2.025179 Validation Loss: 4.485250 Epoch: 9 Training Loss: 2.002646 Validation Loss: 4.398882 Epoch: 10 Training Loss: 1.961583 Validation Loss: 4.332169 Epoch: 11 Training Loss: 1.867792 Validation Loss: 4.302424 Epoch: 12 Training Loss: 1.826433 Validation Loss: 4.472569 Epoch: 13 Training Loss: 1.791796 Validation Loss: 4.465098 Epoch: 14 Training Loss: 1.724154 Validation Loss: 4.470444 Epoch: 15 Training Loss: 1.658189 Validation Loss: 4.536910
<All keys matched successfully>
Try out your model on the test dataset of dog images. Use the code cell below to calculate and print the test loss and accuracy. Ensure that your test accuracy is greater than 10%.
def test(loaders, model, criterion, use_cuda):
# monitor test loss and accuracy
test_loss = 0.
correct = 0.
total = 0.
model.eval()
for batch_idx, (data, target) in enumerate(loaders['test']):
# move to GPU
if use_cuda:
data, target = data.cuda(), target.cuda()
# forward pass: compute predicted outputs by passing inputs to the model
output = model(data)
# calculate the loss
loss = criterion(output, target)
# update average test loss
test_loss = test_loss + ((1 / (batch_idx + 1)) * (loss.data - test_loss))
# convert output probabilities to predicted class
pred = output.data.max(1, keepdim=True)[1]
# compare predictions to true label
correct += np.sum(np.squeeze(pred.eq(target.data.view_as(pred))).cpu().numpy())
total += data.size(0)
print('Test Loss: {:.6f}\n'.format(test_loss))
print('\nTest Accuracy: %2d%% (%2d/%2d)' % (
100. * correct / total, correct, total))
# call test function
test(loaders_scratch, model_scratch, criterion_scratch, use_cuda)
Test Loss: 4.148125 Test Accuracy: 11% (93/836)
You will now use transfer learning to create a CNN that can identify dog breed from images. Your CNN must attain at least 60% accuracy on the test set.
Use the code cell below to write three separate data loaders for the training, validation, and test datasets of dog images (located at dogImages/train, dogImages/valid, and dogImages/test, respectively).
If you like, you are welcome to use the same data loaders from the previous step, when you created a CNN from scratch.
## TODO: Specify data loaders
import os
from torchvision import datasets
### TODO: Write data loaders for training, validation, and test sets
## Specify appropriate transforms, and batch_sizes
batch_size=20
data_dir= './dogImages'
normalizer = transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
# 2- Set the tranformer object
# Augmentation used for training only
train_transform = transforms.Compose([transforms.Resize((224,224)),
transforms.RandomRotation(25),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
normalizer])
# transfor for validation and test images without augmentation
transform = transforms.Compose([transforms.Resize((224,224)),
transforms.ToTensor(),
normalizer])
train_dataset = datasets.ImageFolder(os.path.join(data_dir, 'train/'), transform=train_transform)
valid_dataset = datasets.ImageFolder(os.path.join(data_dir, 'valid/'), transform=transform)
test_dataset = datasets.ImageFolder(os.path.join(data_dir, 'test/'), transform=transform)
train_loader=torch.utils.data.DataLoader(train_dataset,batch_size=batch_size,shuffle=True)
valid_loader=torch.utils.data.DataLoader(valid_dataset,batch_size=batch_size)
test_loader=torch.utils.data.DataLoader(test_dataset,batch_size=batch_size)
loaders_transfer={'train':train_loader,
'valid':valid_loader,
'test':test_loader}
Use transfer learning to create a CNN to classify dog breed. Use the code cell below, and save your initialized model as the variable model_transfer.
import torchvision.models as models
import torch.nn as nn
## TODO: Specify model architecture
model_transfer=models.vgg16(pretrained=True)
print(model_transfer)
VGG(
(features): Sequential(
(0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU(inplace=True)
(4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(6): ReLU(inplace=True)
(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(8): ReLU(inplace=True)
(9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU(inplace=True)
(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(13): ReLU(inplace=True)
(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(15): ReLU(inplace=True)
(16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(18): ReLU(inplace=True)
(19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(20): ReLU(inplace=True)
(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(22): ReLU(inplace=True)
(23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(25): ReLU(inplace=True)
(26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(27): ReLU(inplace=True)
(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(29): ReLU(inplace=True)
(30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
(avgpool): AdaptiveAvgPool2d(output_size=(7, 7))
(classifier): Sequential(
(0): Linear(in_features=25088, out_features=4096, bias=True)
(1): ReLU(inplace=True)
(2): Dropout(p=0.5, inplace=False)
(3): Linear(in_features=4096, out_features=4096, bias=True)
(4): ReLU(inplace=True)
(5): Dropout(p=0.5, inplace=False)
(6): Linear(in_features=4096, out_features=1000, bias=True)
)
)
model_transfer.classifier[6] = nn.Linear(4096, 133)
for param in model_transfer.features.parameters():
param.requires_grad = False
if use_cuda:
model_transfer = model_transfer.cuda()
model_transfer
VGG(
(features): Sequential(
(0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU(inplace=True)
(4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(6): ReLU(inplace=True)
(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(8): ReLU(inplace=True)
(9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU(inplace=True)
(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(13): ReLU(inplace=True)
(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(15): ReLU(inplace=True)
(16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(18): ReLU(inplace=True)
(19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(20): ReLU(inplace=True)
(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(22): ReLU(inplace=True)
(23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(25): ReLU(inplace=True)
(26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(27): ReLU(inplace=True)
(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(29): ReLU(inplace=True)
(30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
(avgpool): AdaptiveAvgPool2d(output_size=(7, 7))
(classifier): Sequential(
(0): Linear(in_features=25088, out_features=4096, bias=True)
(1): ReLU(inplace=True)
(2): Dropout(p=0.5, inplace=False)
(3): Linear(in_features=4096, out_features=4096, bias=True)
(4): ReLU(inplace=True)
(5): Dropout(p=0.5, inplace=False)
(6): Linear(in_features=4096, out_features=133, bias=True)
)
)
Question 5: Outline the steps you took to get to your final CNN architecture and your reasoning at each step. Describe why you think the architecture is suitable for the current problem.
Answer:
Approach:
1-Loading Images in batches.
2-Preparing,Normalizing ,and Transformation.
3-Calling the vgg16 model in its pre-trained form.
4-I Freezed the first layers and took the classifier part to train it on the project 133 dog classes. "param.requires_grad = False".
5-Transfered the model to GPU
Use the next code cell to specify a loss function and optimizer. Save the chosen loss function as criterion_transfer, and the optimizer as optimizer_transfer below.
criterion_transfer = nn.CrossEntropyLoss()
optimizer_transfer = optim.SGD(model_transfer.classifier.parameters(), lr=0.01)
Train and validate your model in the code cell below. Save the final model parameters at filepath 'model_transfer.pt'.
# load the last saved model
model_transfer.load_state_dict(torch.load('model_transfer.pt'))
<All keys matched successfully>
# train the model
n_epochs = 10
model_transfer = train(n_epochs, loaders_transfer, model_transfer, optimizer_transfer, criterion_transfer, use_cuda, 'model_transfer.pt')
# load the model that got the best validation accuracy (uncomment the line below)
model_transfer.load_state_dict(torch.load('model_transfer.pt'))
Epoch: 1 Training Loss: 0.780171 Validation Loss: 0.626818 validation loss decreased from inf to 0.62682 Epoch: 2 Training Loss: 0.664109 Validation Loss: 0.558185 validation loss decreased from 0.62682 to 0.55819 Epoch: 3 Training Loss: 0.570825 Validation Loss: 0.535439 validation loss decreased from 0.55819 to 0.53544 Epoch: 4 Training Loss: 0.493014 Validation Loss: 0.534710 validation loss decreased from 0.53544 to 0.53471 Epoch: 5 Training Loss: 0.457976 Validation Loss: 0.505257 validation loss decreased from 0.53471 to 0.50526 Epoch: 6 Training Loss: 0.428786 Validation Loss: 0.550643 Epoch: 7 Training Loss: 0.384720 Validation Loss: 0.496826 validation loss decreased from 0.50526 to 0.49683 Epoch: 8 Training Loss: 0.339268 Validation Loss: 0.486029 validation loss decreased from 0.49683 to 0.48603 Epoch: 9 Training Loss: 0.321388 Validation Loss: 0.516795 Epoch: 10 Training Loss: 0.294087 Validation Loss: 0.517241
<All keys matched successfully>
Try out your model on the test dataset of dog images. Use the code cell below to calculate and print the test loss and accuracy. Ensure that your test accuracy is greater than 60%.
test(loaders_transfer, model_transfer, criterion_transfer, use_cuda)
Test Loss: 0.578620 Test Accuracy: 83% (702/836)
Write a function that takes an image path as input and returns the dog breed (Affenpinscher, Afghan hound, etc) that is predicted by your model.
### TODO: Write a function that takes a path to an image as input
### and returns the dog breed that is predicted by the model.
# list of class names by index, i.e. a name can be accessed like class_names[0]
class_names = [item[4:].replace("_", " ") for item in train_dataset.classes]
def predict_breed_transfer(img_path):
# load the image and return the predicted breed
# First load the image
img = Image.open(img_path) #.convert('RGB')
# Setup the normalizer
normalizer = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
# Setting up image preprocessor
img_transform = transforms.Compose([transforms.Resize((224, 224)), # Resize the image to 244x244
transforms.ToTensor(), # Convert the numpy array that contains the image into a tensor
normalizer]) # Apply the normalizer
# Apply the preprocessing to the image before passing it to our model
# and add a dummy axis as the model expect a batch of images not a single image
preproccessed_img = img_transform(img)[:3,:,:].unsqueeze(0)
# check if CUDA is available
use_cuda = torch.cuda.is_available()
# move imag to GPU if CUDA is available
if use_cuda:
preproccessed_img = preproccessed_img.cuda()
# Use VGG16 to predict the class of the image
pred = model_transfer(preproccessed_img)
# Move the prediction to cpu and convert it to numpy array and return the index of the class of highest probability
pred = pred.cpu().data.numpy().argmax()
return class_names[pred], pred # return class name and index
Write an algorithm that accepts a file path to an image and first determines whether the image contains a human, dog, or neither. Then,
You are welcome to write your own functions for detecting humans and dogs in images, but feel free to use the face_detector and dog_detector functions developed above. You are required to use your CNN from Step 4 to predict dog breed.
Some sample output for our algorithm is provided below, but feel free to design your own user experience!

### TODO: Write your algorithm.
### Feel free to use as many code cells as needed.
dirs = os.listdir('dogimages/test')
breed_images = []
for dir in dirs:
files = os.listdir('dogimages/test/' + dir)
breed_images.append(os.path.join('dogimages/test/' + dir + '/', files[0]))
def run_app(img_path):
# handle cases for human face, dog, and neither of them
img = Image.open(img_path)
# Use dog_detector to see if there is a dog in the picture first
if dog_detector(img_path):
# get the dog breed
breed, index = predict_breed_transfer(img_path)
# Create the figure to display the picture
fig, ax = plt.subplots(figsize=(5, 5))
# Display the dog picture with it's breed
ax.imshow(img)
ax.set_title(f'The Predicted dog breed is {breed}', fontdict={'fontsize':13})
ax.set_xticks([]); ax.set_yticks([])
elif face_detector(img_path) > 0:
breed, index = predict_breed_transfer(img_path)
# Create a figure for the 2 pics original and a pic for the same predicted breed
fig, ax = plt.subplots(figsize=(9,5), ncols=2)
# Display the original image
ax[0].imshow(img)
ax[0].set_xticks([]); ax[0].set_yticks([])
ax[0].set_title('The Original Image', fontdict={'fontsize':13})
# Display the predicted dog breed image
dog_image = Image.open(breed_images[index])
ax[1].imshow(dog_image)
ax[1].set_title(f'Predicted Dog: {breed}', fontdict={'fontsize':13})
ax[1].set_xticks([]); ax[1].set_yticks([])
fig.text(.2, 0, f'Hi Human do you know that you looks like {breed} dog :)', fontdict={'fontsize':14})
else:
# Displaying the original picture
fig, ax = plt.subplots(figsize=(4, 4))
ax.imshow(img)
ax.set_title(f'Oops! neither dog nor human were found', fontdict={'fontsize':12, 'color':'#ff2020'})
ax.set_xticks([]); ax.set_yticks([])
In this section, you will take your new algorithm for a spin! What kind of dog does the algorithm think that you look like? If you have a dog, does it predict your dog's breed accurately? If you have a cat, does it mistakenly think that your cat is a dog?
Test your algorithm at least six images on your computer. Feel free to use any images you like. Use at least two human and two dog images.
Question 6: Is the output better than you expected :) ? Or worse :( ? Provide at least three possible points of improvement for your algorithm.
Answer: The output is satisfying but not as good as should be ,for examples below points could be improved:
1-More Augmantation could be done to prevent over fitting.
2-Solo Dod images to be provided at early training stage (with no other persons,dogs or objects) to train on dog features only.
3-Another optimization method than SGD could be used to check better accuracy
## TODO: Execute your algorithm from Step 6 on
## at least 6 images on your computer.
## Feel free to use as many code cells as needed.
human_idx = np.random.randint(0, len(human_files), 10)
dog_idx = np.random.randint(0, len(dog_files), 10)
## suggested code, below
for file in np.hstack((human_files[:10], dog_files[:10])):
run_app(file)
## Testing on local images
local_images = np.array(glob("local_imgs/*/*"))
for image in local_images:
run_app(image)